Model reference · open weights

H-optimus-0

Embeddings bioptimus Image embed 1 build Open weights 80k dl/mo

H-optimus-0 is an open-weight embedding model from bioptimus. H-optimus-0 (BF16) weighs 4.5 GB; the smallest configuration that runs it is RTX 3060 12 GB.

  • H-optimus-0 is an open-source foundation model for histology developed by bioptimus.
  • It is a 1.1B parameter vision transformer trained on over 500,000 H&E stained whole slide histology images.
  • The model extracts features from 224x224 pixel images for downstream applications such as mutation prediction, survival analysis, and tissue classification, and is released under the apache-2.0 licence.

Summary of the bioptimus/H-optimus-0 model card, 2026-10-01

What it is

Released bybioptimus
Released2024-07-30
VRAM4.5 GB for the weights

What it runs on

Memory and cards for H-optimus-0 (BF16)

4.5 GBweights, file size
1.1 GBruntime overhead
CardRunsMemory
RTX 3060 12 GBfits11.6 GB
RTX 4060 Ti 16 GBfits15.4 GB
RTX 3090 24 GBfits23.4 GB
RTX 4090 24 GBfits23.4 GB
RTX 5090 32 GBfits31.0 GB
L40S 48 GBfits44.0 GB
A100 80 GBfits78.2 GB
H100 80 GBfits78.1 GB
RTX PRO 6000 Blackwell 96 GBfits93.8 GB
DGX Spark (GB10) 128 GB unifiedfits107 GB
H200 141 GBfits138 GB
B200 180 GBfits176 GB

How it works

How embedding models work

Your textsentence / documentEncodermaps meaningVectorlist of numbersAn embedding model turns text into a vector, so similar meanings sit close together, which is the basis of search and RAG.
© 2026 AxForge · EU-hosted AI infrastructure Pricing Docs Trust Privacy Terms